ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Codestral vs Qwen Plus Character (Japanese) vs Qwen-VL Plus

No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.

Price in rating: Excluded · Include price

  1. Mistral AI

    Codestral

    Released May 29, 2024

    38/100
    • ECI—
    • Price$0.30 / $0.90
    • Context256K
  2. Alibaba (Qwen)

    Qwen Plus Character (Japanese)

    Released Jan 2024

    0/100
    • ECI—
    • Price$0.50 / $1.40
    • Context8K
  3. Alibaba (Qwen)

    Qwen-VL Plus

    Released Jan 25, 2024Deprecated

    43/100
    • ECI—
    • Price$0.21 / $0.63
    • Context131K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Qwen-VL Plus 43/100, Codestral 38/100, Qwen Plus Character (Japanese) 0/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceQwen-VL PlusQwen-VL Plus $0.315 · Codestral $0.45 · Qwen Plus Character (Japanese) $0.725 per 1M tokens (3:1 blend)
  • Longest contextCodestralCodestral 256,000 · Qwen-VL Plus 131,072 · Qwen Plus Character (Japanese) 8,192 tokens
  • Widest inputsQwen-VL PlusCodestral: Text · Qwen Plus Character (Japanese): Text · Qwen-VL Plus: Text, Images
  • Self-hostingCodestralPublishes downloadable weights
How the score is built
MeasureWeightCodestralQwen Plus Character (Japanese)Qwen-VL Plus
Inputs & features60%35050
Context window40%43032
Specs only100%38/1000/10043/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Codestral vs Qwen Plus Character (Japanese) vs Qwen-VL Plus specifications side by side
SpecificationCodestralMistral AIQwen Plus Character (Japanese)Alibaba (Qwen)Qwen-VL PlusAlibaba (Qwen)
Capability
Capabilities Index (ECI)———
ECI rank———
Price per million tokens
Input$0.30$0.50$0.21 (best)
Output$0.90$1.40$0.63 (best)
Cached input$0.03——
Blended (3:1)$0.45$0.725$0.315 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial Mistral APIOfficial Alibaba APIOfficial Alibaba API
Limits
Context window256,000 tokens (best)8,192 tokens131,072 tokens
Max output4,096 tokens512 tokens8,192 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesNoYes
Structured outputYesNoNo
Availability
WeightsOpenProprietaryProprietary
API model IDcodestral-latestqwen-plus-character-jaqwen-vl-plus
API providers4 (best)11
ReleasedMay 29, 2024Jan 2024Jan 25, 2024
Knowledge cutoffOct 2024Apr 2024Apr 2024
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Codestral$4.80
  • Qwen Plus Character (Japanese)$7.80
  • Qwen-VL Plus$3.36
04 — Questions

Which should you choose?

Which is better: Codestral, Qwen Plus Character (Japanese) or Qwen-VL Plus?

There is not enough shared capability evidence to name an overall winner. The scores (Qwen-VL Plus 43/100, Codestral 38/100, Qwen Plus Character (Japanese) 0/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Codestral, Qwen Plus Character (Japanese) or Qwen-VL Plus?

Qwen-VL Plus is cheaper at $0.21 input / $0.63 output per million tokens (official Alibaba API price). Codestral costs $0.30 input / $0.90 output per million tokens (official Mistral API price); Qwen Plus Character (Japanese) costs $0.50 input / $1.40 output per million tokens (official Alibaba API price). At a typical mix of three input tokens to one output token, that is $0.315 per million tokens for Qwen-VL Plus versus $0.45 for Codestral (1.4× as much) and $0.725 for Qwen Plus Character (Japanese) (2.3× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Codestral has not been scored yet, Qwen Plus Character (Japanese) has not been scored yet and Qwen-VL Plus has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Codestral, Qwen Plus Character (Japanese) and Qwen-VL Plus yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Qwen Plus Character (Japanese) does not support tool calling, which most coding agents need.

Which has the bigger context window?

Codestral has the largest context window at 256,000 tokens, against 131,072 for Qwen-VL Plus and 8,192 for Qwen Plus Character (Japanese). Maximum output per response: Codestral up to 4,096, Qwen Plus Character (Japanese) up to 512, Qwen-VL Plus up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Codestral accepts text; Qwen Plus Character (Japanese) accepts text; Qwen-VL Plus accepts text and images. Qwen-VL Plus handles the widest range of inputs.

Are any of these open source?

Codestral publishes its weights and can be self-hosted; Qwen Plus Character (Japanese) and Qwen-VL Plus is proprietary.

Which is newer?

Codestral is the newest, released May 29, 2024. Qwen-VL Plus came out Jan 25, 2024; Qwen Plus Character (Japanese) came out Jan 2024. Knowledge cutoff: Codestral Oct 2024, Qwen Plus Character (Japanese) Apr 2024, Qwen-VL Plus Apr 2024.

How do you decide the winner?

This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 18, 2026.